Repeated Games against Budgeted Adversaries
نویسندگان
چکیده
We study repeated zero-sum games against an adversary on a budget. Given that an adversary has some constraint on the sequence of actions that he plays, we consider what ought to be the player’s best mixed strategy with knowledge of this budget. We show that, for a general class of normal-form games, the minimax strategy is indeed efficiently computable and relies on a “random playout” technique. We give three diverse applications of this new algorithmic template: a cost-sensitive “Hedge” setting, a particular problem in Metrical Task Systems, and the design of combinatorial prediction markets.
منابع مشابه
Repeated Games against Budgeted Adversaries
We study repeated zero-sum games against an adversary on a budget. Given that an adversary is constrained by the amount he can play each action, we consider what ought to be the player’s best mixed strategy with knowledge of this budget. We show that, for a general class of normal-form games, the minimax strategy is indeed efficiently computable and relies on a simple random walk.
متن کاملEecient Algorithms for Learning to Play Repeated Games against Computationally Bounded Adversaries
We study the problem of eeciently learning to play a game optimally against an unknown adversary chosen from a computationally bounded class. We both contribute to the line of research on playing games against nite automata, and expand the scope of this research by considering new classes of adversaries. We introduce the natural notions of games against recent history adversaries (whose current...
متن کاملConvergence, Targeted Optimality, and Safety in Multiagent Learning
This paper introduces a novel multiagent learning algorithm, Convergence with Model Learning and Safety (or CMLeS in short), which achieves convergence, targeted optimality against memory-bounded adversaries, and safety, in arbitrary repeated games. The most novel aspect of CMLeS is the manner in which it guarantees (in a PAC sense) targeted optimality against memory-bounded adversaries, via ef...
متن کاملSequential targeted optimality as a new criterion for teaching and following in repeated games
In infinitely repeated games, the act of teaching an outcome to our adversaries can be beneficial to reach coordination, as well as allowing us to ‘steer’ adversaries to outcomes that are more beneficial to us. Teaching works well against followers, agents that are willing to go along with the proposal, but can lead to miscoordination otherwise. In the context of infinitely repeated games there...
متن کاملToward Addressing Collusion Among Human Adversaries in Security Games
Security agencies including the US Coast Guard, the Federal Air Marshal Service and the Los Angeles Airport police are several major domains that have been deploying Stackelberg security games and related algorithms to protect against a single adversary or multiple, independent adversaries strategically. However, there are a variety of real-world security domains where adversaries may benefit f...
متن کامل